Upload 9 files
Browse files- adapter_config.json +17 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +912 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "/scratch/hpc103a02/workspace/pretrain-model/open-llama-7b",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "LORA",
|
| 11 |
+
"r": 8,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"q_proj",
|
| 14 |
+
"v_proj"
|
| 15 |
+
],
|
| 16 |
+
"task_type": "CAUSAL_LM"
|
| 17 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
|
| 3 |
+
size 443
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf4ba9bc189cafe2dd56e0d1033dcfce0a0217b2df3c6bdb94ff97f780670b25
|
| 3 |
+
size 33661637
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b45c00bf50c33e0cdd89810818c3a4c38f334480c5406cf874ac5c8e2a62e9ac
|
| 3 |
+
size 16822989
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3159831570831bad1d9f1d4f927dd461f017c9e8296a191299b01118f68feca4
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16fdfc03b58220402968eacaac23fb5471cdb9061302380bd3c8d4d326c02ade
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1df92ec5a7817609c17c5cee1ddaa66dbca5f5c8b5450a69b483d8d86176699
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,912 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.500215470790863,
|
| 3 |
+
"best_model_checkpoint": "./MT-deer-7B/checkpoint-1400",
|
| 4 |
+
"epoch": 2.662546059669559,
|
| 5 |
+
"global_step": 1400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 1.4291,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 1.3933,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 1.3044,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.08,
|
| 30 |
+
"learning_rate": 0.00011999999999999999,
|
| 31 |
+
"loss": 1.1498,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.1,
|
| 36 |
+
"learning_rate": 0.00015,
|
| 37 |
+
"loss": 0.9306,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11,
|
| 42 |
+
"learning_rate": 0.00017999999999999998,
|
| 43 |
+
"loss": 0.8534,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13,
|
| 48 |
+
"learning_rate": 0.00020999999999999998,
|
| 49 |
+
"loss": 0.8292,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.15,
|
| 54 |
+
"learning_rate": 0.00023999999999999998,
|
| 55 |
+
"loss": 0.8054,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.17,
|
| 60 |
+
"learning_rate": 0.00027,
|
| 61 |
+
"loss": 0.7794,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.19,
|
| 66 |
+
"learning_rate": 0.0003,
|
| 67 |
+
"loss": 0.7457,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.21,
|
| 72 |
+
"learning_rate": 0.0002979661016949152,
|
| 73 |
+
"loss": 0.7358,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.23,
|
| 78 |
+
"learning_rate": 0.0002959322033898305,
|
| 79 |
+
"loss": 0.729,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.25,
|
| 84 |
+
"learning_rate": 0.0002938983050847457,
|
| 85 |
+
"loss": 0.7056,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.27,
|
| 90 |
+
"learning_rate": 0.000291864406779661,
|
| 91 |
+
"loss": 0.6986,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.29,
|
| 96 |
+
"learning_rate": 0.00028983050847457623,
|
| 97 |
+
"loss": 0.6859,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.3,
|
| 102 |
+
"learning_rate": 0.0002877966101694915,
|
| 103 |
+
"loss": 0.6639,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.32,
|
| 108 |
+
"learning_rate": 0.00028576271186440673,
|
| 109 |
+
"loss": 0.6708,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.34,
|
| 114 |
+
"learning_rate": 0.000283728813559322,
|
| 115 |
+
"loss": 0.6593,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.36,
|
| 120 |
+
"learning_rate": 0.00028169491525423723,
|
| 121 |
+
"loss": 0.6497,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.38,
|
| 126 |
+
"learning_rate": 0.0002796610169491525,
|
| 127 |
+
"loss": 0.6432,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.38,
|
| 132 |
+
"eval_loss": 0.642841637134552,
|
| 133 |
+
"eval_runtime": 92.942,
|
| 134 |
+
"eval_samples_per_second": 21.519,
|
| 135 |
+
"eval_steps_per_second": 2.69,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.4,
|
| 140 |
+
"learning_rate": 0.00027762711864406773,
|
| 141 |
+
"loss": 0.6384,
|
| 142 |
+
"step": 210
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.42,
|
| 146 |
+
"learning_rate": 0.00027559322033898304,
|
| 147 |
+
"loss": 0.6344,
|
| 148 |
+
"step": 220
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.44,
|
| 152 |
+
"learning_rate": 0.0002735593220338983,
|
| 153 |
+
"loss": 0.6308,
|
| 154 |
+
"step": 230
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.46,
|
| 158 |
+
"learning_rate": 0.00027152542372881354,
|
| 159 |
+
"loss": 0.6239,
|
| 160 |
+
"step": 240
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.48,
|
| 164 |
+
"learning_rate": 0.0002694915254237288,
|
| 165 |
+
"loss": 0.6229,
|
| 166 |
+
"step": 250
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.49,
|
| 170 |
+
"learning_rate": 0.00026745762711864404,
|
| 171 |
+
"loss": 0.6149,
|
| 172 |
+
"step": 260
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.51,
|
| 176 |
+
"learning_rate": 0.0002654237288135593,
|
| 177 |
+
"loss": 0.6062,
|
| 178 |
+
"step": 270
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.53,
|
| 182 |
+
"learning_rate": 0.00026338983050847454,
|
| 183 |
+
"loss": 0.615,
|
| 184 |
+
"step": 280
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.55,
|
| 188 |
+
"learning_rate": 0.0002613559322033898,
|
| 189 |
+
"loss": 0.6043,
|
| 190 |
+
"step": 290
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.57,
|
| 194 |
+
"learning_rate": 0.0002593220338983051,
|
| 195 |
+
"loss": 0.6004,
|
| 196 |
+
"step": 300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.59,
|
| 200 |
+
"learning_rate": 0.00025728813559322035,
|
| 201 |
+
"loss": 0.6058,
|
| 202 |
+
"step": 310
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.61,
|
| 206 |
+
"learning_rate": 0.0002552542372881356,
|
| 207 |
+
"loss": 0.5902,
|
| 208 |
+
"step": 320
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 0.63,
|
| 212 |
+
"learning_rate": 0.00025322033898305085,
|
| 213 |
+
"loss": 0.5912,
|
| 214 |
+
"step": 330
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.65,
|
| 218 |
+
"learning_rate": 0.0002511864406779661,
|
| 219 |
+
"loss": 0.5988,
|
| 220 |
+
"step": 340
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.67,
|
| 224 |
+
"learning_rate": 0.00024915254237288135,
|
| 225 |
+
"loss": 0.5806,
|
| 226 |
+
"step": 350
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.68,
|
| 230 |
+
"learning_rate": 0.0002471186440677966,
|
| 231 |
+
"loss": 0.5879,
|
| 232 |
+
"step": 360
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.7,
|
| 236 |
+
"learning_rate": 0.00024508474576271185,
|
| 237 |
+
"loss": 0.5846,
|
| 238 |
+
"step": 370
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.72,
|
| 242 |
+
"learning_rate": 0.0002430508474576271,
|
| 243 |
+
"loss": 0.5789,
|
| 244 |
+
"step": 380
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.74,
|
| 248 |
+
"learning_rate": 0.00024101694915254235,
|
| 249 |
+
"loss": 0.5787,
|
| 250 |
+
"step": 390
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.76,
|
| 254 |
+
"learning_rate": 0.0002389830508474576,
|
| 255 |
+
"loss": 0.5802,
|
| 256 |
+
"step": 400
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.76,
|
| 260 |
+
"eval_loss": 0.5802366137504578,
|
| 261 |
+
"eval_runtime": 93.7341,
|
| 262 |
+
"eval_samples_per_second": 21.337,
|
| 263 |
+
"eval_steps_per_second": 2.667,
|
| 264 |
+
"step": 400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.78,
|
| 268 |
+
"learning_rate": 0.00023694915254237286,
|
| 269 |
+
"loss": 0.5854,
|
| 270 |
+
"step": 410
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.8,
|
| 274 |
+
"learning_rate": 0.0002349152542372881,
|
| 275 |
+
"loss": 0.5757,
|
| 276 |
+
"step": 420
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.82,
|
| 280 |
+
"learning_rate": 0.00023288135593220336,
|
| 281 |
+
"loss": 0.572,
|
| 282 |
+
"step": 430
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.84,
|
| 286 |
+
"learning_rate": 0.0002308474576271186,
|
| 287 |
+
"loss": 0.5626,
|
| 288 |
+
"step": 440
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.86,
|
| 292 |
+
"learning_rate": 0.00022881355932203386,
|
| 293 |
+
"loss": 0.5605,
|
| 294 |
+
"step": 450
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.87,
|
| 298 |
+
"learning_rate": 0.0002267796610169491,
|
| 299 |
+
"loss": 0.5656,
|
| 300 |
+
"step": 460
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.89,
|
| 304 |
+
"learning_rate": 0.0002247457627118644,
|
| 305 |
+
"loss": 0.5592,
|
| 306 |
+
"step": 470
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.91,
|
| 310 |
+
"learning_rate": 0.00022271186440677964,
|
| 311 |
+
"loss": 0.5639,
|
| 312 |
+
"step": 480
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.93,
|
| 316 |
+
"learning_rate": 0.0002206779661016949,
|
| 317 |
+
"loss": 0.5616,
|
| 318 |
+
"step": 490
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.95,
|
| 322 |
+
"learning_rate": 0.00021864406779661014,
|
| 323 |
+
"loss": 0.5677,
|
| 324 |
+
"step": 500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.97,
|
| 328 |
+
"learning_rate": 0.00021661016949152542,
|
| 329 |
+
"loss": 0.5562,
|
| 330 |
+
"step": 510
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.99,
|
| 334 |
+
"learning_rate": 0.00021457627118644067,
|
| 335 |
+
"loss": 0.5535,
|
| 336 |
+
"step": 520
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.01,
|
| 340 |
+
"learning_rate": 0.00021254237288135592,
|
| 341 |
+
"loss": 0.5604,
|
| 342 |
+
"step": 530
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.03,
|
| 346 |
+
"learning_rate": 0.00021050847457627117,
|
| 347 |
+
"loss": 0.5507,
|
| 348 |
+
"step": 540
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.05,
|
| 352 |
+
"learning_rate": 0.00020847457627118642,
|
| 353 |
+
"loss": 0.5434,
|
| 354 |
+
"step": 550
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.07,
|
| 358 |
+
"learning_rate": 0.0002064406779661017,
|
| 359 |
+
"loss": 0.5517,
|
| 360 |
+
"step": 560
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.08,
|
| 364 |
+
"learning_rate": 0.00020440677966101695,
|
| 365 |
+
"loss": 0.5459,
|
| 366 |
+
"step": 570
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.1,
|
| 370 |
+
"learning_rate": 0.0002023728813559322,
|
| 371 |
+
"loss": 0.548,
|
| 372 |
+
"step": 580
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.12,
|
| 376 |
+
"learning_rate": 0.00020033898305084745,
|
| 377 |
+
"loss": 0.5463,
|
| 378 |
+
"step": 590
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.14,
|
| 382 |
+
"learning_rate": 0.0001983050847457627,
|
| 383 |
+
"loss": 0.5402,
|
| 384 |
+
"step": 600
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.14,
|
| 388 |
+
"eval_loss": 0.5485313534736633,
|
| 389 |
+
"eval_runtime": 93.9991,
|
| 390 |
+
"eval_samples_per_second": 21.277,
|
| 391 |
+
"eval_steps_per_second": 2.66,
|
| 392 |
+
"step": 600
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.16,
|
| 396 |
+
"learning_rate": 0.00019627118644067795,
|
| 397 |
+
"loss": 0.541,
|
| 398 |
+
"step": 610
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.18,
|
| 402 |
+
"learning_rate": 0.0001942372881355932,
|
| 403 |
+
"loss": 0.5471,
|
| 404 |
+
"step": 620
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.2,
|
| 408 |
+
"learning_rate": 0.00019220338983050845,
|
| 409 |
+
"loss": 0.536,
|
| 410 |
+
"step": 630
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.22,
|
| 414 |
+
"learning_rate": 0.0001901694915254237,
|
| 415 |
+
"loss": 0.5386,
|
| 416 |
+
"step": 640
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.24,
|
| 420 |
+
"learning_rate": 0.00018813559322033895,
|
| 421 |
+
"loss": 0.5337,
|
| 422 |
+
"step": 650
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.26,
|
| 426 |
+
"learning_rate": 0.0001861016949152542,
|
| 427 |
+
"loss": 0.5351,
|
| 428 |
+
"step": 660
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.27,
|
| 432 |
+
"learning_rate": 0.00018406779661016948,
|
| 433 |
+
"loss": 0.5225,
|
| 434 |
+
"step": 670
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.29,
|
| 438 |
+
"learning_rate": 0.00018203389830508473,
|
| 439 |
+
"loss": 0.5366,
|
| 440 |
+
"step": 680
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.31,
|
| 444 |
+
"learning_rate": 0.00017999999999999998,
|
| 445 |
+
"loss": 0.5323,
|
| 446 |
+
"step": 690
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.33,
|
| 450 |
+
"learning_rate": 0.00017796610169491523,
|
| 451 |
+
"loss": 0.5316,
|
| 452 |
+
"step": 700
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.35,
|
| 456 |
+
"learning_rate": 0.00017593220338983049,
|
| 457 |
+
"loss": 0.5385,
|
| 458 |
+
"step": 710
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.37,
|
| 462 |
+
"learning_rate": 0.00017389830508474574,
|
| 463 |
+
"loss": 0.5293,
|
| 464 |
+
"step": 720
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.39,
|
| 468 |
+
"learning_rate": 0.000171864406779661,
|
| 469 |
+
"loss": 0.5233,
|
| 470 |
+
"step": 730
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.41,
|
| 474 |
+
"learning_rate": 0.00016983050847457624,
|
| 475 |
+
"loss": 0.5135,
|
| 476 |
+
"step": 740
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.43,
|
| 480 |
+
"learning_rate": 0.0001677966101694915,
|
| 481 |
+
"loss": 0.5266,
|
| 482 |
+
"step": 750
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 1.45,
|
| 486 |
+
"learning_rate": 0.00016576271186440674,
|
| 487 |
+
"loss": 0.5266,
|
| 488 |
+
"step": 760
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.46,
|
| 492 |
+
"learning_rate": 0.000163728813559322,
|
| 493 |
+
"loss": 0.5217,
|
| 494 |
+
"step": 770
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.48,
|
| 498 |
+
"learning_rate": 0.0001616949152542373,
|
| 499 |
+
"loss": 0.5149,
|
| 500 |
+
"step": 780
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.5,
|
| 504 |
+
"learning_rate": 0.00015966101694915255,
|
| 505 |
+
"loss": 0.5239,
|
| 506 |
+
"step": 790
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.52,
|
| 510 |
+
"learning_rate": 0.0001576271186440678,
|
| 511 |
+
"loss": 0.5202,
|
| 512 |
+
"step": 800
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.52,
|
| 516 |
+
"eval_loss": 0.5286936163902283,
|
| 517 |
+
"eval_runtime": 94.1069,
|
| 518 |
+
"eval_samples_per_second": 21.252,
|
| 519 |
+
"eval_steps_per_second": 2.657,
|
| 520 |
+
"step": 800
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.54,
|
| 524 |
+
"learning_rate": 0.00015559322033898305,
|
| 525 |
+
"loss": 0.5321,
|
| 526 |
+
"step": 810
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.56,
|
| 530 |
+
"learning_rate": 0.0001535593220338983,
|
| 531 |
+
"loss": 0.5203,
|
| 532 |
+
"step": 820
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.58,
|
| 536 |
+
"learning_rate": 0.00015152542372881355,
|
| 537 |
+
"loss": 0.5205,
|
| 538 |
+
"step": 830
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.6,
|
| 542 |
+
"learning_rate": 0.0001494915254237288,
|
| 543 |
+
"loss": 0.5255,
|
| 544 |
+
"step": 840
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.62,
|
| 548 |
+
"learning_rate": 0.00014745762711864405,
|
| 549 |
+
"loss": 0.5164,
|
| 550 |
+
"step": 850
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.64,
|
| 554 |
+
"learning_rate": 0.00014542372881355933,
|
| 555 |
+
"loss": 0.5182,
|
| 556 |
+
"step": 860
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.65,
|
| 560 |
+
"learning_rate": 0.00014338983050847458,
|
| 561 |
+
"loss": 0.5171,
|
| 562 |
+
"step": 870
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.67,
|
| 566 |
+
"learning_rate": 0.00014135593220338983,
|
| 567 |
+
"loss": 0.5172,
|
| 568 |
+
"step": 880
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.69,
|
| 572 |
+
"learning_rate": 0.00013932203389830508,
|
| 573 |
+
"loss": 0.5171,
|
| 574 |
+
"step": 890
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.71,
|
| 578 |
+
"learning_rate": 0.00013728813559322033,
|
| 579 |
+
"loss": 0.5114,
|
| 580 |
+
"step": 900
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.73,
|
| 584 |
+
"learning_rate": 0.00013525423728813558,
|
| 585 |
+
"loss": 0.5079,
|
| 586 |
+
"step": 910
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.75,
|
| 590 |
+
"learning_rate": 0.00013322033898305083,
|
| 591 |
+
"loss": 0.5158,
|
| 592 |
+
"step": 920
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.77,
|
| 596 |
+
"learning_rate": 0.00013118644067796608,
|
| 597 |
+
"loss": 0.5128,
|
| 598 |
+
"step": 930
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.79,
|
| 602 |
+
"learning_rate": 0.00012915254237288133,
|
| 603 |
+
"loss": 0.5198,
|
| 604 |
+
"step": 940
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.81,
|
| 608 |
+
"learning_rate": 0.00012711864406779658,
|
| 609 |
+
"loss": 0.5063,
|
| 610 |
+
"step": 950
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.83,
|
| 614 |
+
"learning_rate": 0.00012508474576271184,
|
| 615 |
+
"loss": 0.5068,
|
| 616 |
+
"step": 960
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.84,
|
| 620 |
+
"learning_rate": 0.00012305084745762709,
|
| 621 |
+
"loss": 0.5136,
|
| 622 |
+
"step": 970
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.86,
|
| 626 |
+
"learning_rate": 0.00012101694915254236,
|
| 627 |
+
"loss": 0.5012,
|
| 628 |
+
"step": 980
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.88,
|
| 632 |
+
"learning_rate": 0.00011898305084745763,
|
| 633 |
+
"loss": 0.5071,
|
| 634 |
+
"step": 990
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.9,
|
| 638 |
+
"learning_rate": 0.00011694915254237288,
|
| 639 |
+
"loss": 0.5092,
|
| 640 |
+
"step": 1000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.9,
|
| 644 |
+
"eval_loss": 0.514962375164032,
|
| 645 |
+
"eval_runtime": 93.8613,
|
| 646 |
+
"eval_samples_per_second": 21.308,
|
| 647 |
+
"eval_steps_per_second": 2.664,
|
| 648 |
+
"step": 1000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.92,
|
| 652 |
+
"learning_rate": 0.00011491525423728813,
|
| 653 |
+
"loss": 0.5185,
|
| 654 |
+
"step": 1010
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.94,
|
| 658 |
+
"learning_rate": 0.00011288135593220338,
|
| 659 |
+
"loss": 0.5055,
|
| 660 |
+
"step": 1020
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.96,
|
| 664 |
+
"learning_rate": 0.00011084745762711863,
|
| 665 |
+
"loss": 0.5078,
|
| 666 |
+
"step": 1030
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.98,
|
| 670 |
+
"learning_rate": 0.00010881355932203388,
|
| 671 |
+
"loss": 0.5092,
|
| 672 |
+
"step": 1040
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 2.0,
|
| 676 |
+
"learning_rate": 0.00010677966101694915,
|
| 677 |
+
"loss": 0.4933,
|
| 678 |
+
"step": 1050
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 2.02,
|
| 682 |
+
"learning_rate": 0.0001047457627118644,
|
| 683 |
+
"loss": 0.5052,
|
| 684 |
+
"step": 1060
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.03,
|
| 688 |
+
"learning_rate": 0.00010271186440677965,
|
| 689 |
+
"loss": 0.4914,
|
| 690 |
+
"step": 1070
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.05,
|
| 694 |
+
"learning_rate": 0.0001006779661016949,
|
| 695 |
+
"loss": 0.4962,
|
| 696 |
+
"step": 1080
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 2.07,
|
| 700 |
+
"learning_rate": 9.864406779661015e-05,
|
| 701 |
+
"loss": 0.4969,
|
| 702 |
+
"step": 1090
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 2.09,
|
| 706 |
+
"learning_rate": 9.661016949152541e-05,
|
| 707 |
+
"loss": 0.5053,
|
| 708 |
+
"step": 1100
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 2.11,
|
| 712 |
+
"learning_rate": 9.457627118644068e-05,
|
| 713 |
+
"loss": 0.4934,
|
| 714 |
+
"step": 1110
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.13,
|
| 718 |
+
"learning_rate": 9.254237288135593e-05,
|
| 719 |
+
"loss": 0.4864,
|
| 720 |
+
"step": 1120
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 2.15,
|
| 724 |
+
"learning_rate": 9.050847457627118e-05,
|
| 725 |
+
"loss": 0.4974,
|
| 726 |
+
"step": 1130
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.17,
|
| 730 |
+
"learning_rate": 8.847457627118644e-05,
|
| 731 |
+
"loss": 0.4985,
|
| 732 |
+
"step": 1140
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.19,
|
| 736 |
+
"learning_rate": 8.64406779661017e-05,
|
| 737 |
+
"loss": 0.4945,
|
| 738 |
+
"step": 1150
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 2.21,
|
| 742 |
+
"learning_rate": 8.440677966101695e-05,
|
| 743 |
+
"loss": 0.4986,
|
| 744 |
+
"step": 1160
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 2.23,
|
| 748 |
+
"learning_rate": 8.23728813559322e-05,
|
| 749 |
+
"loss": 0.4887,
|
| 750 |
+
"step": 1170
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.24,
|
| 754 |
+
"learning_rate": 8.033898305084745e-05,
|
| 755 |
+
"loss": 0.5004,
|
| 756 |
+
"step": 1180
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.26,
|
| 760 |
+
"learning_rate": 7.83050847457627e-05,
|
| 761 |
+
"loss": 0.486,
|
| 762 |
+
"step": 1190
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 2.28,
|
| 766 |
+
"learning_rate": 7.627118644067796e-05,
|
| 767 |
+
"loss": 0.4863,
|
| 768 |
+
"step": 1200
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.28,
|
| 772 |
+
"eval_loss": 0.5064148902893066,
|
| 773 |
+
"eval_runtime": 93.4587,
|
| 774 |
+
"eval_samples_per_second": 21.4,
|
| 775 |
+
"eval_steps_per_second": 2.675,
|
| 776 |
+
"step": 1200
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.3,
|
| 780 |
+
"learning_rate": 7.423728813559321e-05,
|
| 781 |
+
"loss": 0.4959,
|
| 782 |
+
"step": 1210
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.32,
|
| 786 |
+
"learning_rate": 7.220338983050848e-05,
|
| 787 |
+
"loss": 0.4961,
|
| 788 |
+
"step": 1220
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.34,
|
| 792 |
+
"learning_rate": 7.016949152542373e-05,
|
| 793 |
+
"loss": 0.4902,
|
| 794 |
+
"step": 1230
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.36,
|
| 798 |
+
"learning_rate": 6.813559322033898e-05,
|
| 799 |
+
"loss": 0.4957,
|
| 800 |
+
"step": 1240
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.38,
|
| 804 |
+
"learning_rate": 6.610169491525423e-05,
|
| 805 |
+
"loss": 0.4998,
|
| 806 |
+
"step": 1250
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.4,
|
| 810 |
+
"learning_rate": 6.406779661016948e-05,
|
| 811 |
+
"loss": 0.4945,
|
| 812 |
+
"step": 1260
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.42,
|
| 816 |
+
"learning_rate": 6.203389830508473e-05,
|
| 817 |
+
"loss": 0.4914,
|
| 818 |
+
"step": 1270
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 2.43,
|
| 822 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 823 |
+
"loss": 0.4984,
|
| 824 |
+
"step": 1280
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.45,
|
| 828 |
+
"learning_rate": 5.796610169491525e-05,
|
| 829 |
+
"loss": 0.4926,
|
| 830 |
+
"step": 1290
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.47,
|
| 834 |
+
"learning_rate": 5.59322033898305e-05,
|
| 835 |
+
"loss": 0.4891,
|
| 836 |
+
"step": 1300
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.49,
|
| 840 |
+
"learning_rate": 5.389830508474576e-05,
|
| 841 |
+
"loss": 0.4895,
|
| 842 |
+
"step": 1310
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.51,
|
| 846 |
+
"learning_rate": 5.186440677966101e-05,
|
| 847 |
+
"loss": 0.4817,
|
| 848 |
+
"step": 1320
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.53,
|
| 852 |
+
"learning_rate": 4.983050847457626e-05,
|
| 853 |
+
"loss": 0.491,
|
| 854 |
+
"step": 1330
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.55,
|
| 858 |
+
"learning_rate": 4.779661016949152e-05,
|
| 859 |
+
"loss": 0.4878,
|
| 860 |
+
"step": 1340
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 2.57,
|
| 864 |
+
"learning_rate": 4.576271186440678e-05,
|
| 865 |
+
"loss": 0.4869,
|
| 866 |
+
"step": 1350
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 2.59,
|
| 870 |
+
"learning_rate": 4.3728813559322035e-05,
|
| 871 |
+
"loss": 0.488,
|
| 872 |
+
"step": 1360
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.61,
|
| 876 |
+
"learning_rate": 4.1694915254237285e-05,
|
| 877 |
+
"loss": 0.4866,
|
| 878 |
+
"step": 1370
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.62,
|
| 882 |
+
"learning_rate": 3.9661016949152536e-05,
|
| 883 |
+
"loss": 0.4892,
|
| 884 |
+
"step": 1380
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.64,
|
| 888 |
+
"learning_rate": 3.7627118644067794e-05,
|
| 889 |
+
"loss": 0.486,
|
| 890 |
+
"step": 1390
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.66,
|
| 894 |
+
"learning_rate": 3.559322033898305e-05,
|
| 895 |
+
"loss": 0.4879,
|
| 896 |
+
"step": 1400
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.66,
|
| 900 |
+
"eval_loss": 0.500215470790863,
|
| 901 |
+
"eval_runtime": 93.9201,
|
| 902 |
+
"eval_samples_per_second": 21.295,
|
| 903 |
+
"eval_steps_per_second": 2.662,
|
| 904 |
+
"step": 1400
|
| 905 |
+
}
|
| 906 |
+
],
|
| 907 |
+
"max_steps": 1575,
|
| 908 |
+
"num_train_epochs": 3,
|
| 909 |
+
"total_flos": 1.8195722467776922e+18,
|
| 910 |
+
"trial_name": null,
|
| 911 |
+
"trial_params": null
|
| 912 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75348781713c0ab7b61f8d4b6cb04aa9248df139ecbb3589461f5ef75a6fa662
|
| 3 |
+
size 3899
|